this post was submitted on 29 Jul 2025
29 points (91.4% liked)
Programming
22218 readers
371 users here now
Welcome to the main community in programming.dev! Feel free to post anything relating to programming here!
Cross posting is strongly encouraged in the instance. If you feel your post or another person's post makes sense in another community cross post into it.
Hope you enjoy the instance!
Rules
Rules
- Follow the programming.dev instance rules
- Keep content related to programming in some way
- If you're posting long videos try to add in some form of tldr for those who don't want to watch videos
Wormhole
Follow the wormhole through a path of communities !webdev@programming.dev
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
And how do you know that the LLM was accurate and gave you the correct information, instead of just making up something entirely novel and telling you what you wanted to hear? Maybe the detail you were searching for could not be found, because it did not actually exist.
He said he clicked the source it quoted.
Maybe if Google hasn't been enshittifying search for 10 years, AI search wouldn't be useful. But I've seen the same thing. The forced Gemini summary at the top of Google often has source links that aren't anywhere on the first page of Google itself.
And how do you know the source is accurate? Having a source doesn't automatically make it accurate. Bullshit can also have sources.
The premise of the op is that classic programming makes AI unnecessary. Having a bad source from classic Google search index isn't a problem with AI.
First, read my text fully before replying.
But additionally I have a brain and can use it to double check:
In example 1. I just build it blindly because it's a game and it doesn't matter if it's wrong. But it ended up being correct and I ended up having more fun instead of doing excel for an hour.
In 2. the math result was not far off from my guesstimate and I confirmed later, it was correct.
In 3. it gave me a source and I read the source. Google did not lead me to that source.
When I let LLM write code, I read the code, then I test the code. Here is where I get the most faults. Not in spreadsheets or math or research.
It's weird how there is such a knee jerk hate for a turbo charged word predictor. You'd think there would have been similar mouth frothing at on screen keyboards predicting words.
I see it as a tool that helps sometimes. It's like an electric drill and craftsmen are screaming, "BUT YOU COULD DRILL OFF CENTER!!!"
The commenter more or less admitted that they have no way of knowing that the algorithm is actually correct.
In your first analogy it would be like if text predictors pulled words from a thesaurus instead of a list of common words.
He tested it and it was good enough for him. If he wrote the code he'd still not know if it was correct and need to test it. If knowing an algorithm was all that was needed for writing working code, there wouldn't have been any software bugs in all of computer history until AI.
My phone keyboard text predictor lists 3 words and they're frequently wrong. At best it lists 3 and you have to choose the 1 right word.